huggingface / huggingface/setfit
Prediction Interpretability
Open
- Dominant language
- Jupyter Notebook
- Stars
- 2.8k
- Forks
- 267
- Avg merge
- 36m
- Merged PRs (30d)
- 5
Description
Has anyone looked into the interpretability of setfit models?
I'm wondering if you can do things like visualizing attention to see which words have the most influence in predicting a particular class.
Any direction would be appreciated!
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.